trueskill-tt/tests/prediction_guards.rs

//! No prediction path may answer from a fit it cannot answer from.
//!
//! `converge` grew a `NonFiniteResult` guard; nothing stopped a caller from
//! ignoring that error and predicting anyway. The three failures that produced
//! were each differently wrong: `Ok(NaN)`, a panic out of a `Result`-returning
//! method, and `Ok([0.0, 0.0])` — finite, plausible, summing to zero against a
//! doc that promises one.
//!
//! Every test here has a healthy control, so none can pass by everything
//! returning `Err`.

use trueskill_tt::{
    ConstantDrift, Event, Gaussian, History, InferenceError, Member, NullObserver, Outcome, Team,
};

type H = History<i64, ConstantDrift, NullObserver, &'static str>;

fn build(beta: f64, prior: Option<Gaussian>, outcome: Outcome) -> H {
    let mut h: H = History::builder()
        .beta(beta)
        .drift(ConstantDrift::new(0.0))
        .build();

    let member = |k: &'static str| match prior {
        Some(p) => Member::new(k).with_prior(p),
        None => Member::new(k),
    };

    let _ = h.add_events(vec![Event {
        time: 1,
        teams: [
            Team::with_members([member("a")]),
            Team::with_members([member("b")]),
        ]
        .into_iter()
        .collect(),
        outcome,
    }]);
    h
}

/// Point-mass priors with `beta(0.0)` on a *ranked* event: `converge` reports
/// `NonFiniteResult` and the stored posteriors are `pi: NaN, tau: NaN`.
fn nan_poisoned() -> H {
    let mut h = build(
        0.0,
        Some(Gaussian::from_ms(0.0, 0.0)),
        Outcome::winner(0, 2),
    );
    let err = h.converge().expect_err("this fixture must not converge");
    assert!(
        matches!(err, InferenceError::NonFiniteResult { .. }),
        "{err:?}"
    );
    h
}

/// The same degenerate parameters on a *scored* event, where inference
/// converges cleanly and leaves legitimate point-mass posteriors behind. The
/// fit is fine; it is prediction that has nothing to work with.
fn degenerate_but_converged() -> H {
    let mut h = build(
        0.0,
        Some(Gaussian::from_ms(0.0, 0.0)),
        Outcome::scores([1.0, 0.0]),
    );
    h.converge().expect("this fixture converges");
    h
}

fn healthy() -> H {
    let mut h = build(1.0, None, Outcome::winner(0, 2));
    h.converge().expect("control converges");
    h
}

macro_rules! all_predictions {
    ($h:ident, $f:expr) => {{
        let teams: &[&[&&'static str]] = &[&[&"a"], &[&"b"]];
        let f = $f;
        f("predict_quality", $h.predict_quality(teams).map(|_| ()));
        f(
            "predict_win_probabilities",
            $h.predict_win_probabilities(teams).map(|_| ()),
        );
        f("predict_outcome", $h.predict_outcome(teams).map(|_| ()));
        f(
            "predict_ranking",
            $h.predict_ranking(teams, &[0, 1]).map(|_| ()),
        );
        f(
            "expected_information_gain",
            $h.expected_information_gain(teams).map(|_| ()),
        );
    }};
}

#[test]
fn a_nan_poisoned_fit_is_refused_by_every_prediction_path() {
    let h = nan_poisoned();

    all_predictions!(h, |name: &str, r: Result<(), InferenceError>| {
        match r {
            Err(InferenceError::NonFiniteResult { .. }) => {}
            other => panic!("{name} answered from a NaN fit: {other:?}"),
        }
    });
}

#[test]
fn degenerate_performances_are_refused_rather_than_answered_wrongly() {
    let h = degenerate_but_converged();

    // The fit itself is sound — the posteriors are point masses, not NaN.
    let skill = h.current_skill("a").expect("a played");
    assert_eq!(skill.sigma(), 0.0);
    assert!(skill.mu().is_finite());

    // `predict_quality` previously PANICKED here, out of a method that returns
    // `Result`: the contrast covariance is exactly singular when beta is zero
    // and every skill is a point mass.
    all_predictions!(h, |name: &str, r: Result<(), InferenceError>| {
        match r {
            Err(InferenceError::InvalidParameter { .. }) => {}
            other => panic!("{name} predicted from a degenerate fit: {other:?}"),
        }
    });
}

#[test]
fn the_control_history_answers_every_prediction() {
    let h = healthy();

    all_predictions!(h, |name: &str, r: Result<(), InferenceError>| {
        assert!(r.is_ok(), "{name} failed on a healthy history: {r:?}");
    });
}

#[test]
fn win_probabilities_sum_to_one_on_the_control() {
    // The promise the `Ok([0.0, 0.0])` case broke. Asserted on the control so
    // the guard above cannot be "fixed" by making every path error.
    let h = healthy();
    let p = h
        .predict_win_probabilities(&[&[&"a"], &[&"b"]])
        .expect("control predicts");
    let total: f64 = p.iter().sum();
    assert!(
        (total - 1.0).abs() < 1e-6,
        "win probabilities sum to {total}"
    );
}